Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.8359. Min Act: -0.0000

Data Index: 25663 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.5602. Min Act: -0.0000

Data Index: 610815 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.2630. Min Act: -0.0000

Data Index: 1035835 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4283. Min Act: -0.0000

Data Index: 396166 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4405. Min Act: -0.0000

Data Index: 630721 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3926. Min Act: -0.0000

Data Index: 1584191 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 3.8359. Min Range: -3.8359

Max Act: 2.9449. Min Act: -0.0000

Data Index: 876173 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3493. Min Act: -0.0000

Data Index: 1076701 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.0113. Min Act: -0.0000

Data Index: 1592444 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.5655. Min Act: -0.0000

Data Index: 1637103 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3762. Min Act: -0.0000

Data Index: 1960903 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1990. Min Act: -0.0000

Data Index: 19091 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1907. Min Act: -0.0000

Data Index: 1047427 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3079. Min Act: -0.0000

Data Index: 833555 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4417. Min Act: -0.0000

Data Index: 1582387 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.2645. Min Act: -0.0000

Data Index: 801806 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 3.8359. Min Range: -3.8359

Max Act: 2.8354. Min Act: -0.0000

Data Index: 1451121 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 3.8359. Min Range: -3.8359

Max Act: 2.8171. Min Act: -0.0000

Data Index: 969959 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 3.8359. Min Range: -3.8359

Max Act: 2.9386. Min Act: -0.0000

Data Index: 1982709 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.0798. Min Act: -0.0000

Data Index: 292133 (The Pile)

Max Activating Token Index: 493